Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3938 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.4679. Min Act: -0.0000

Data Index: 719414 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.4542. Min Act: -0.0000

Data Index: 931424 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.4316. Min Act: -0.0000

Data Index: 612597 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1107240 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.4483. Min Act: -0.0000

Data Index: 969821 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1261002 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.4110. Min Act: -0.0000

Data Index: 466522 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.4018. Min Act: -0.0000

Data Index: 435071 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.4264. Min Act: -0.0000

Data Index: 588553 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3974. Min Act: -0.0000

Data Index: 434423 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1286876 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3847. Min Act: -0.0000

Data Index: 804526 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3507. Min Act: -0.0000

Data Index: 578326 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1293242 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3350. Min Act: -0.0000

Data Index: 194269 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3525. Min Act: -0.0000

Data Index: 401806 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1350877 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3089. Min Act: -0.0000

Data Index: 81949 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.2899. Min Act: -0.0000

Data Index: 547722 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.4679. Min Range: -0.4679

Max Act: 0.3085. Min Act: -0.0000

Data Index: 361825 (C4 (Web Text))

Max Activating Token Index: 80